[go: up one dir, main page]

CN118169071A - Pill roller drying end point prediction method and system - Google Patents

Pill roller drying end point prediction method and system Download PDF

Info

Publication number
CN118169071A
CN118169071A CN202410105334.9A CN202410105334A CN118169071A CN 118169071 A CN118169071 A CN 118169071A CN 202410105334 A CN202410105334 A CN 202410105334A CN 118169071 A CN118169071 A CN 118169071A
Authority
CN
China
Prior art keywords
drying
pills
spectrum data
data
matrix
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202410105334.9A
Other languages
Chinese (zh)
Inventor
刘淑
韩立云
徐娜
傅少山
崔文雅
宋立平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinyao Darentang Group Co ltd Darentang Pharmaceutical Factory
Original Assignee
Jinyao Darentang Group Co ltd Darentang Pharmaceutical Factory
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinyao Darentang Group Co ltd Darentang Pharmaceutical Factory filed Critical Jinyao Darentang Group Co ltd Darentang Pharmaceutical Factory
Priority to CN202410105334.9A priority Critical patent/CN118169071A/en
Publication of CN118169071A publication Critical patent/CN118169071A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/27—Regression, e.g. linear or logistic regression
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention relates to the technical field of medicament preparation, in particular to a pill roller drying end point prediction method and a pill roller drying end point prediction system, wherein the prediction method comprises the following steps: s1: collecting historical drying data, comprising: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding; s2: preprocessing near infrared spectrum data of pills in different batches during feeding, and extracting features of the preprocessed spectrum data to obtain extracted feature spectrum data; based on the extracted characteristic spectrum data, a drying endpoint regression prediction model of the characteristic spectrum data and the number of the discharging drying roller is established; s3: and inputting near infrared spectrum data of the to-be-predicted batch of pills into the drying end point prediction model to obtain the number of the discharging drying roller of the to-be-predicted batch of pills. The invention can avoid the problem of misjudging the discharging time by manpower, and saves time and labor cost.

Description

Pill roller drying end point prediction method and system
Technical Field
The invention relates to the technical field of medicament preparation, in particular to a pill roller drying end point prediction method and system.
Background
The drum-type pill dryer is currently used in mass production of pharmaceutical factories, has good drying effect, the drum is driven by the transmission mechanism to do forward and reverse movement, pills to be dried enter the drum from one end of the drum, a material guide plate is arranged in the drum, and the dried pills are discharged from the other end of the drum under the action of the material guide plate. The material is dried in a moving state due to the rotation of the roller, so that the heated material is uniformly dried at a high speed, and the shape of the material is not changed. The rotating speed of the roller can be adjusted at will, and proper drying conditions such as temperature, wind speed and the like can be set. However, the pill materials input into the drying section from the previous section have the problem of water content difference, the time length reaching the drying end point also has larger difference, and if the fixed discharging time is used, the output materials have the problem of inconsistent water content among batches (overdry or insufficient drying); if different equipment parameters or drying time are required, real-time state parameters of materials are lacking, and other pharmaceutical drying equipment such as online moisture detection instruments for fluidized bed drying are difficult to install due to the high-speed rotation characteristic of the roller drying equipment.
In order to solve the problem, at present, a plurality of drying drums are connected in series, partial materials are taken out from equipment to detect moisture, the moisture release standard is achieved, the materials are discharged, if the moisture release standard is not achieved, the materials are continuously conveyed into the next drying drum to be dried again, and the like until the moisture release requirement is met. This approach has been greatly improved over a single drying drum, but multiple moisture detection is time-consuming and labor-consuming.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defect that a water release detection module is not arranged in a production section in the prior art, and the water release time of pills is determined manually according to experience.
In order to solve the technical problems, the invention provides a pill roller drying end point prediction method and a system, which can predict a roller drying end point through a mathematical algorithm and provide reference for a water division detection node so as to avoid time consumption of repeated water detection, wherein the method comprises the following steps:
S1: collecting historical drying data, comprising: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding;
s2: based on the historical drying data, constructing a drying endpoint prediction model, comprising:
Constructing an initial matrix Z by utilizing near infrared spectrum data of pills in different batches during feeding, preprocessing the initial matrix Z to obtain a preprocessed spectrum matrix X, wherein the behavior spectrum number of the spectrum matrix X is the number of wavelength points;
extracting features of the pretreated spectrum matrix X to obtain extracted feature spectrum data;
Based on the characteristic spectrum data of pills in different batches and the serial numbers of the pills which are discharged from the drying roller, corresponding to the batches and reach the water release standard, a regression equation of the characteristic spectrum data and the serial numbers of the discharging drying roller is established, namely a drying end point prediction model:
wherein Y represents the number of the discharging drying roller, N represents the number of spectra, also the number of lines of the characteristic spectrum data; k represents the dimension of the characteristic spectrum data; a 1、a2、...、ak and b are preset coefficients; s 1,n、s2,n、...、sk,n represents matrix elements in the characteristic spectrum data; thres represents a preset threshold;
s3: and inputting near infrared spectrum data of the to-be-predicted batch of pills into the drying end point prediction model to obtain the number of the discharging drying roller of the to-be-predicted batch of pills.
In one embodiment of the invention, a method of collecting near infrared spectrum data for different batches of pills at the time of feeding includes: scanning different batches of pills to obtain original near infrared spectrum curves of different batches of pills, and obtaining final near infrared spectrum data of different batches of pills by measuring background single-channel spectrum, scanning for multiple times and taking average value to reduce errors of spectrum data.
In one embodiment of the present invention, a method of preprocessing an initial matrix Z includes: and preprocessing the initial matrix Z by adopting a moving window smoothing and standard normal transformation algorithm.
In one embodiment of the present invention, the method for acquiring the characteristic spectrum data includes: and carrying out data dimension reduction on the preprocessed spectrum matrix X by utilizing principal component analysis, and extracting characteristic information in the preprocessed spectrum matrix, namely the characteristic spectrum data.
In one embodiment of the present invention, the method for performing data dimension reduction on the preprocessed spectrum matrix X by using the principal component analysis method includes:
Pretreated spectrum matrix Where x ij is the nth dimensional variable of the mth spectral sample data, normalize x ij:
Wherein i=1, m; j=1.. n; Is the mean value; s j is the variance;
Calculating a covariance matrix based on the normalized spectrum matrix X, and according to the eigenvalue of the covariance matrix and the corresponding eigenvector;
And arranging the eigenvectors into a matrix according to the corresponding eigenvalues from top to bottom, and taking the first k rows to form a matrix P to obtain the reduced-dimension spectral data S=PX *＝[s1,s2,...,sk.
In one embodiment of the present invention, the dimension of the reduced-dimension spectral data is determined according to the magnitude of the eigenvalue.
Based on the same inventive concept, the invention also provides a pill roller drying end point prediction system, which comprises the following modules:
the data collection module is used for collecting historical drying data and comprises: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding;
The drying end point prediction model construction module is used for constructing a drying end point prediction model based on the historical drying data;
and the drying end point prediction module is used for inputting near infrared spectrum data of the batch of pills to be predicted into the drying end point prediction model to obtain the number of the discharging drying roller of the batch of pills to be predicted.
The invention also provides an electronic device, which comprises a processor, a memory and a bus system, wherein the processor and the memory are connected through the bus system, the memory is used for storing instructions, and the processor is used for executing the instructions stored by the memory so as to realize the pill roller drying end point prediction method.
The invention also provides a pill moisture detection device which comprises the electronic equipment, and the electronic equipment is used for controlling the opening of the release channel of the drying roller.
The present invention also provides a computer storage medium storing a computer software product comprising instructions for causing a computer device to perform the pill roller drying endpoint prediction method.
Compared with the prior art, the technical scheme of the invention has the following advantages:
the method solves the problems of complex steps and long time consumption in the water detection process generated by estimating the material drying end point by manual experience in the prior art, predicts the water end point by using a mathematical method, and further achieves more accurate medicament discharge time of the water release standard.
Drawings
In order that the invention may be more readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof that are illustrated in the appended drawings, in which
FIG. 1 is a flow chart of a method for predicting pill roller drying endpoint in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of raw near infrared spectrum data for different batches of pills at the time of feeding collected in an embodiment of the present invention;
FIG. 3 is a schematic diagram of near infrared spectrum data after preprocessing by using a moving window smoothing (MAF) and standard normal transformation (SNV) method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of contribution rates of main components when feature information of the preprocessed near infrared spectrum data is extracted by using a main component analysis method in an embodiment of the present invention;
FIG. 5 is a diagram of raw near infrared spectrum data of a batch of lung-heat clearing and anti-inflammatory pills to be predicted according to an embodiment of the present invention;
FIG. 6 is a block diagram of a pill roller drying endpoint prediction system provided in an embodiment of the invention;
Description of the specification reference numerals: 100. a data acquisition module; 200. a drying end point prediction model construction module; 300. and a drying end point prediction module.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and specific examples, which are not intended to be limiting, so that those skilled in the art will better understand the invention and practice it.
Example 1
Referring to fig. 1, in this embodiment, taking a lung-heat clearing and inflammation diminishing pill as an example, a method and a system for predicting a pill roller drying end point are provided, wherein the roller drying end point can be predicted by a mathematical algorithm, and a reference is provided to a water division detection node so as to avoid time consumption of repeated water detection, and the method comprises the following steps:
S1: collecting historical drying data, comprising: collecting near infrared spectrum data (shown in figure 2) of pills of different batches when feeding, and discharging the pills which correspond to the batches and reach the moisture release standard out of the number of the drying roller;
s2: based on the historical drying data, constructing a drying endpoint prediction model, comprising:
Constructing an initial matrix Z by utilizing near infrared spectrum data of pills in different batches during feeding, preprocessing the initial matrix Z by adopting a moving window smoothing and standard normal transformation algorithm, wherein the preprocessed spectrum data also corresponds to a preprocessed spectrum matrix X as shown in figure 3, and the behavior spectrum number of the spectrum matrix X is listed as the number of wavelength points;
extracting features of the pretreated spectrum matrix X to obtain extracted feature spectrum data;
Based on the characteristic spectrum data of pills in different batches and the serial numbers of the pills which are discharged from the drying roller, corresponding to the batches and reach the water release standard, a regression equation of the characteristic spectrum data and the serial numbers of the discharging drying roller is established, namely a drying end point prediction model:
wherein Y represents the number of the discharging drying roller, N represents the number of spectra, also the number of lines of the characteristic spectrum data; k represents the dimension of the characteristic spectrum data; a 1、a2、...、ak and b are preset coefficients; s 1,n、s2,n、...、sk,n represents matrix elements in the characteristic spectrum data; thres represents a preset threshold;
s3: and inputting near infrared spectrum data of the to-be-predicted batch of pills into the drying end point prediction model to obtain the number of the discharging drying roller of the to-be-predicted batch of pills.
In this example, the method of collecting near infrared spectrum data for different batches of pills at the time of feeding includes: scanning different batches of pills to obtain original near infrared spectrum curves of different batches of pills, and obtaining final near infrared spectrum data of different batches of pills by measuring background single-channel spectrum, scanning for multiple times and taking average value to reduce errors of spectrum data.
In this embodiment, the method for acquiring the characteristic spectrum data includes: and carrying out data dimension reduction on the preprocessed spectrum matrix X by utilizing principal component analysis, and extracting characteristic information in the preprocessed spectrum matrix, namely the characteristic spectrum data.
The method for carrying out data dimension reduction on the pretreated spectrum matrix X by using the principal component analysis method comprises the following steps:
Pretreated spectrum matrix Where x ij is the nth dimensional variable of the mth spectral sample data, normalize x ij:
Wherein i=1, m; j=1.. n; Is the mean value; s j is the variance;
Calculating a covariance matrix based on the normalized spectrum matrix X, and according to the eigenvalue of the covariance matrix and the corresponding eigenvector;
And arranging the eigenvectors into a matrix according to the corresponding eigenvalues from top to bottom, and taking the first k rows to form a matrix P to obtain the reduced-dimension spectral data S=PX *＝[s1,s2,...,sk. The dimension of the spectrum data after dimension reduction is determined according to the size of the characteristic value.
The pretreatment spectral data was reduced in dimension using the principal component analysis method described above, and as can be seen from fig. 4, the contribution rate of the first four principal components reached 98%, thus reducing the spectral data to 4 dimensions. Taking the scores of the first four main components to correspond to the discharging time and establishing a regression model:
Yi＝0.1192s1+0.0384s2+0.0742s3+0.212s4+5.7423
wherein s1, s2, s3 and s4 are the spectrum data scores after dimension reduction.
Near infrared spectrum data of a new batch of lung-heat clearing and inflammation diminishing pills are collected, as shown in fig. 5, after dimension reduction, the main component scores of the pills are led into the regression model, and a predicted result Y=6 of the number of the discharging drying roller is obtained.
Example two
Based on the same inventive concept as in the first embodiment, the present invention also provides a pill roller drying end point prediction system, as shown in fig. 6, comprising the following modules:
An acquisition data module 100 for collecting historical drying data, comprising: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding;
A drying endpoint prediction model construction module 200, configured to construct a drying endpoint prediction model based on the historical drying data;
And the drying end point prediction module 300 is used for inputting near infrared spectrum data of the batch of pills to be predicted into the drying end point prediction model to obtain the number of the discharging drying roller of the batch of pills to be predicted.
The present embodiment provides a pill roller drying endpoint prediction system for implementing the pill roller drying endpoint prediction method, so that the specific implementation of the pill roller drying endpoint prediction system may be found in the foregoing example portions of the pill roller drying endpoint prediction method, for example, the acquisition data module 100, the drying endpoint prediction model building module 200, and the drying endpoint prediction module 300 are respectively used for corresponding to steps S1, S2, and S3 in the pill roller drying endpoint prediction method in the implementation embodiment one, so that the specific implementation thereof may refer to the description of the corresponding respective portion embodiments, and in order to avoid redundancy, the details will not be repeated here.
Example III
The invention also provides an electronic device, which comprises a processor, a memory and a bus system, wherein the processor and the memory are connected through the bus system, the memory is used for storing instructions, and the processor is used for executing the instructions stored by the memory so as to realize the pill roller drying end point prediction method in the first embodiment.
Example IV
The invention also provides a pill moisture detection device which comprises the electronic equipment in the third embodiment, and the electronic equipment is used for controlling the opening of the release channel of the drying roller.
Example five
The present invention also provides a computer storage medium storing a computer software product comprising instructions for causing a computer device to perform the method of pill roller drying endpoint prediction described in embodiment one.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations and modifications of the present invention will be apparent to those of ordinary skill in the art in light of the foregoing description. It is not necessary here nor is it exhaustive of all embodiments. And obvious variations or modifications thereof are contemplated as falling within the scope of the present invention.

Claims (10)

1. A method of predicting a pill roller drying endpoint comprising:
S1: collecting historical drying data, comprising: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding;
s2: based on the historical drying data, constructing a drying endpoint prediction model, comprising:
Constructing an initial matrix Z by utilizing near infrared spectrum data of pills in different batches during feeding, preprocessing the initial matrix Z to obtain a preprocessed spectrum matrix X, wherein the behavior spectrum number of the spectrum matrix X is the number of wavelength points;
extracting features of the pretreated spectrum matrix X to obtain extracted feature spectrum data;
Based on the characteristic spectrum data of pills in different batches and the serial numbers of the pills which are discharged from the drying roller, corresponding to the batches and reach the water release standard, a regression equation of the characteristic spectrum data and the serial numbers of the discharging drying roller is established, namely a drying end point prediction model:
wherein Y represents the number of the discharging drying roller, N represents the number of spectra, also the number of lines of the characteristic spectrum data; k represents the dimension of the characteristic spectrum data; a 1、a2、...、ak and b are preset coefficients; s 1,n、s2,n、...、sk,n represents matrix elements in the characteristic spectrum data; thres represents a preset threshold;
s3: and inputting near infrared spectrum data of the to-be-predicted batch of pills into the drying end point prediction model to obtain the number of the discharging drying roller of the to-be-predicted batch of pills.
2. The pill roller drying endpoint prediction method according to claim 1, wherein: the method for collecting near infrared spectrum data of pills of different batches during feeding comprises the following steps: scanning different batches of pills to obtain original near infrared spectrum curves of different batches of pills, and obtaining final near infrared spectrum data of different batches of pills by measuring background single-channel spectrum, scanning for multiple times and taking average value to reduce errors of spectrum data.
3. The pill roller drying endpoint prediction method according to claim 1, wherein: the method for preprocessing the initial matrix Z comprises the following steps: and preprocessing the initial matrix Z by adopting a moving window smoothing and standard normal transformation algorithm.
4. A method of predicting pill roller drying endpoint according to any one of claims 1 to 3, wherein: the method for acquiring the characteristic spectrum data comprises the following steps: and carrying out data dimension reduction on the preprocessed spectrum matrix X by utilizing principal component analysis, and extracting characteristic information in the preprocessed spectrum matrix, namely the characteristic spectrum data.
5. The pill roller drying endpoint prediction method according to claim 4, wherein: the method for carrying out data dimension reduction on the pretreated spectrum matrix X by using the principal component analysis method comprises the following steps:
Pretreated spectrum matrix Where x ij is the nth dimensional variable of the mth spectral sample data, normalize x ij:
Wherein i=1, m; j=1.. n; Is the mean value; s j is the variance;
Calculating a covariance matrix based on the normalized spectrum matrix X, and according to the eigenvalue of the covariance matrix and the corresponding eigenvector;
And arranging the eigenvectors into a matrix according to the corresponding eigenvalues from top to bottom, and taking the first k rows to form a matrix P to obtain the reduced-dimension spectral data S=PX *＝[s1,s2,...,sk.
6. The pill roller drying endpoint prediction method according to claim 6, wherein: the dimension of the spectrum data after dimension reduction is determined according to the size of the characteristic value.
7. A pill roller drying endpoint prediction system comprising the following modules:
the data collection module is used for collecting historical drying data and comprises: collecting near infrared spectrum data of pills of different batches and numbers of pill discharge drying drums which correspond to the batches and reach the water release standard during feeding;
The drying end point prediction model construction module is used for constructing a drying end point prediction model based on the historical drying data;
and the drying end point prediction module is used for inputting near infrared spectrum data of the batch of pills to be predicted into the drying end point prediction model to obtain the number of the discharging drying roller of the batch of pills to be predicted.
8. An electronic device comprising a processor, a memory and a bus system, the processor and the memory being connected by the bus system, the memory being for storing instructions, the processor being for executing the instructions stored by the memory to implement the pill roller drying endpoint prediction method of any one of claims 1 to 7.
9. A pill moisture detection apparatus comprising an electronic device according to claim 8, wherein the electronic device is used to control the opening of the release passage of the drying drum.
10. A computer storage medium having stored thereon a computer software product comprising instructions for causing a computer device to perform the pill roller drying endpoint prediction method according to any one of claims 1 to 7.
CN202410105334.9A 2024-01-25 2024-01-25 Pill roller drying end point prediction method and system Pending CN118169071A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410105334.9A CN118169071A (en) 2024-01-25 2024-01-25 Pill roller drying end point prediction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410105334.9A CN118169071A (en) 2024-01-25 2024-01-25 Pill roller drying end point prediction method and system

Publications (1)

Publication Number Publication Date
CN118169071A true CN118169071A (en) 2024-06-11

Family

ID=91357572

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410105334.9A Pending CN118169071A (en) 2024-01-25 2024-01-25 Pill roller drying end point prediction method and system

Country Status (1)

Country Link
CN (1) CN118169071A (en)

Similar Documents

Publication Publication Date Title
EP3788446B1 (en) Computer system and method for automated batch data alignment in batch process modeling, monitoring and control
Chakraborty et al. Development of an optimally designed real-time automatic citrus fruit grading–sorting​ machine leveraging computer vision-based adaptive deep learning model
CN117743772B (en) Toilet paper drying parameter optimization method and system based on artificial intelligent model
CN112317110A (en) Ore grinding granularity prediction system and method based on deep learning
EP3933513A1 (en) Prediction control development device, prediction control development method, and prediction control development program
JP2023507906A (en) Method and control system for controlling polymer viscosity quality
CN108629091B (en) Mill load parameter prediction method based on selective fusion multichannel mechanical signal frequency spectrum multi-feature subset
JPH05324006A (en) Device and method of controlling process
KR102528505B1 (en) Customized Autonomous Artificial Intelligence Platform Using Manufacturing Process Data
CN118466422A (en) System and method for optimizing and controlling extraction process of agilawood effective components
CN118437494B (en) Optimized control method and system for feed crushing equipment
CN116258080A (en) Method and device for predicting outlet water content of sheet cut-tobacco dryer
CN106372412A (en) Energy efficiency analysis system of interlocking equipment
CN119310895B (en) A fully automatic online PAT continuous crystallization control method, medium and system
CN118169071A (en) Pill roller drying end point prediction method and system
EP4328684A1 (en) Predicting a batch quality value by a machine learning model for a dedicated batch of material in a production line
He et al. Freshness evaluation of cucumber and carrot using hyperspectral imaging and portable near-infrared spectrometers with deep learning
CN114139813A (en) Flow type production equipment product quality prediction method based on self-updating model
Záhonyi et al. Explainable artificial neural network as a soft sensor to predict the moisture content in a continuous granulation line
CN120220866A (en) A method for predicting multi-component content of polymers based on multi-branch neural network
Arunachalam et al. End-to-end industrial IoT: software optimization and acceleration
CN117763465A (en) A cold chain food epidemic prevention detection system and method
CN118500104A (en) Intelligent red date processing method and equipment
CN120124429B (en) Blade root load prediction method, device, equipment and medium of wind turbine generator
Sturm et al. Towards a System View on Intelligent Drying

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination